INDEX

Explanations

indications of errors related to network requests

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sizeCache

-0.84

 sumpay

-0.83

oredCriteria

-0.78

ⓧ

-0.76

IVEREF

-0.75

 deschis

-0.73

 saites

-0.73

 Audiodateien

-0.73

ыгана

-0.72

 Autorizaciones

-0.71

POSITIVE LOGITS

 الاطلاع

0.61

0.50

ParallelGroup

0.49

>::

0.49

 CYTHON

0.46

}}}\

0.46

DateTimeField

0.45

“

0.45

orthy

0.45

0.44

Activations Density 0.214%

indications of errors related to network requests

No Comments

No Known Activations